Internal API instruction following (OpenAI)
Models answer prompts drawn from real developer use cases that carry instructions on formatting, verbosity and length. OpenAI reports a hard subset.
OpenAI introduced it with GPT-4.1 on 2025-04-14 and reported it again in the GPT-5 developer post on 2025-08-07. The grading method is not described, so model-judged is assumed.
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
GPT-5 mini leads with 65.8% among models released by Aug 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Aug 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 GPT-5 mini 65.8%
- 2 GPT-5 nano 56.1%
- 3 GPT-4.1 mini 45.1%
- 4 GPT-4.1 nano 31.6%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 mini | 65.8% | Aug 2025 | Model card | |
| 2 | GPT-5 nano | 56.1% | Aug 2025 | Model card | |
| 3 | GPT-4.1 mini | 45.1% | Apr 2025 | Model card | |
| 4 | GPT-4.1 nano | 31.6% | Apr 2025 | Model card |
2 models have held number one since its release in Apr 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Aug 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 7 Aug 2025 | GPT-5 nano | 56.1 | Internal API instruction following eval (hard) |
| 7 Aug 2025 | GPT-5 mini | 65.8 | Internal API instruction following eval (hard) |
| 14 Apr 2025 | GPT-4.1 nano | 31.6 | Internal API instruction following (hard) |
| 14 Apr 2025 | GPT-4.1 mini | 45.1 | Internal API instruction following (hard) |
More in Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9% - IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose).
Nemotron-Cascade 2 30B-A3B 82.9% - MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85% - IFStruct In use Models generate JSON or YAML that must follow a requested schema and phrasing constraints, without constrained decoding. A response passes only if every structural constraint holds. LFM3-1.7B 93.7%